Unverified Commit b2c090cc authored by Minho Ryu's avatar Minho Ryu Committed by GitHub
Browse files

aggregate by group (total and categories) (#2643)

parent ed9c6fc8
dataset_name: agricultural_sciences
include: _hard_kmmlu_yaml
task: kmmlu_hard_agricultural_sciences
tag: kmmlu_hard_other_tasks
dataset_name: aviation_engineering_and_maintenance
include: _hard_kmmlu_yaml
task: kmmlu_hard_aviation_engineering_and_maintenance
tag: kmmlu_hard_applied_science_tasks
dataset_name: biology
include: _hard_kmmlu_yaml
task: kmmlu_hard_biology
tag: kmmlu_hard_stem_tasks
dataset_name: chemical_engineering
include: _hard_kmmlu_yaml
task: kmmlu_hard_chemical_engineering
tag: kmmlu_hard_stem_tasks
dataset_name: chemistry
include: _hard_kmmlu_yaml
task: kmmlu_hard_chemistry
tag: kmmlu_hard_stem_tasks
dataset_name: civil_engineering
include: _hard_kmmlu_yaml
task: kmmlu_hard_civil_engineering
tag: kmmlu_hard_stem_tasks
dataset_name: computer_science
include: _hard_kmmlu_yaml
task: kmmlu_hard_computer_science
tag: kmmlu_hard_stem_tasks
dataset_name: construction
include: _hard_kmmlu_yaml
task: kmmlu_hard_construction
tag: kmmlu_hard_other_tasks
dataset_name: criminal_law
include: _hard_kmmlu_yaml
task: kmmlu_hard_criminal_law
tag: kmmlu_hard_humss_tasks
dataset_name: ecology
include: _hard_kmmlu_yaml
task: kmmlu_hard_ecology
tag: kmmlu_hard_stem_tasks
dataset_name: economics
include: _hard_kmmlu_yaml
task: kmmlu_hard_economics
tag: kmmlu_hard_humss_tasks
dataset_name: education
include: _hard_kmmlu_yaml
task: kmmlu_hard_education
tag: kmmlu_hard_humss_tasks
dataset_name: electrical_engineering
include: _hard_kmmlu_yaml
task: kmmlu_hard_electrical_engineering
tag: kmmlu_hard_stem_tasks
dataset_name: electronics_engineering
include: _hard_kmmlu_yaml
task: kmmlu_hard_electronics_engineering
tag: kmmlu_hard_applied_science_tasks
dataset_name: energy_management
include: _hard_kmmlu_yaml
task: kmmlu_hard_energy_management
tag: kmmlu_hard_applied_science_tasks
dataset_name: environmental_science
include: _hard_kmmlu_yaml
task: kmmlu_hard_environmental_science
tag: kmmlu_hard_applied_science_tasks
dataset_name: fashion
include: _hard_kmmlu_yaml
task: kmmlu_hard_fashion
tag: kmmlu_hard_other_tasks
dataset_name: food_processing
include: _hard_kmmlu_yaml
task: kmmlu_hard_food_processing
tag: kmmlu_hard_other_tasks
dataset_name: gas_technology_and_engineering
include: _hard_kmmlu_yaml
task: kmmlu_hard_gas_technology_and_engineering
tag: kmmlu_hard_applied_science_tasks
dataset_name: geomatics
include: _hard_kmmlu_yaml
task: kmmlu_hard_geomatics
tag: kmmlu_hard_applied_science_tasks
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment